70680c9f93
Model: laion/openthoughts-4-code-qwen3-32b-annotated-32k_qwen3-1.7B_32k Source: Original Platform
36 lines
949 B
Markdown
36 lines
949 B
Markdown
---
|
|
license: apache-2.0
|
|
datasets:
|
|
- laion/openthoughts-4-code-qwen3-32b-32k-annotated
|
|
base_model:
|
|
- Qwen/Qwen3-1.7B
|
|
---
|
|
|
|
Test Qwen3 1.7B post-trained on laion/openthoughts-4-code-qwen3-32b-32k-annotated (Qwen3 32B 32k output length annotated, using https://huggingface.co/datasets/mlfoundations-dev/hero_run_4_code as seed for generation)
|
|
|
|
## Training procedure
|
|
|
|
### Training hyperparameters
|
|
|
|
The following hyperparameters were used during training:
|
|
- learning_rate: 0.00015
|
|
- per_device_train_batch_size: 1
|
|
- seed: 42
|
|
- distributed_type: multi-GPU
|
|
- num_devices: 256
|
|
- total_train_batch_size: 256
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.99) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
|
- lr_scheduler_type: cosine
|
|
- lr_scheduler_warmup_ratio: 0.1
|
|
- num_epochs: 2.0
|
|
|
|
### Training results
|
|
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.55.0
|
|
- Pytorch 2.7.1+cu128
|
|
- Datasets 3.6.0
|
|
- Tokenizers 0.21.1 |